# DeepSeek R1

DeepSeek R1 was last priced at $0.70 per million input tokens and $2.50 per million output tokens, as of October 22, 2026. None of the 6 coding benchmarks behind the index has measured it, so it has no coding index, but 51 benchmarks outside the index have a result below.

Page: https://llmbenchmark.ai/models/deepseek-r1
Data from October 22, 2026. Every figure below names the board it was read from and the day.

- Maker: DeepSeek
- Released: January 20, 2025
- Price per million input tokens: $0.70
- Price per million output tokens: $2.50
- Context window: 64K tokens
- Status: retired. No longer listed on OpenRouter since October 19, 2026; last listed price shown.

Benchmark results (51 of 195):

- Aider polyglot: 56.9% (source: Aider polyglot leaderboard, read October 22, 2026)
- AIME: 74.0% (source: AIME (Vals AI), read October 22, 2026)
- MMLU Pro: 83.2% (source: MMLU Pro (Vals AI), read October 22, 2026)
- LiveCodeBench (Vals AI): 70.2% (source: Vals AI boards, read October 22, 2026)
- MATH 500 (Vals AI): 92.2% (source: Vals AI boards, read October 22, 2026)
- MGSM (Vals AI): 92.3% (source: Vals AI boards, read October 22, 2026)
- LegalBench (Vals AI): 67.3% (source: Vals AI boards, read October 22, 2026)
- CorpFin (Vals AI): 54.1% (source: Vals AI boards, read October 22, 2026)
- TaxEval (Vals AI): 72.3% (source: Vals AI boards, read October 22, 2026)
- MedQA (Vals AI): 90.8% (source: Vals AI boards, read October 22, 2026)
- WeirdML: 36.5% (source: Epoch AI benchmarking hub, read October 22, 2026)
- METR time horizons: 51.9% (source: Epoch AI benchmarking hub, read October 22, 2026)
- BALROG: 34.9% (source: Epoch AI benchmarking hub, read October 22, 2026)
- GPQA Diamond (Epoch AI run): 71.7% (source: Epoch AI benchmarking hub, read October 22, 2026)
- ARC-AGI: 15.8% (source: Epoch AI benchmarking hub, read October 22, 2026)
- ARC-AGI-2: 1.3% (source: Epoch AI benchmarking hub, read October 22, 2026)
- SimpleBench: 30.9% (source: Epoch AI benchmarking hub, read October 22, 2026)
- OTIS Mock AIME: 53.3% (source: Epoch AI benchmarking hub, read October 22, 2026)
- MATH level 5: 93.1% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Fiction.LiveBench: 69.4% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Creative writing (Lech Mazur): 83.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Epoch Capabilities Index: 138.8 (source: Epoch AI benchmarking hub, read October 22, 2026)
- LMArena Text: 1373 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: coding: 1371 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts: 1361 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: math: 1393 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: instruction following: 1357 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: creative writing: 1354 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: English: 1385 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: non-English: 1357 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Chinese: 1400 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: German: 1384 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Japanese: 1324 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Korean: 1329 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: French: 1367 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Spanish: 1379 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Russian: 1354 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: multi-turn: 1391 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: longer queries: 1355 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: expert: 1338 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts in English: 1375 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: software and IT: 1375 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: mathematical work: 1389 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: science: 1375 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: medicine and healthcare: 1371 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: legal and government: 1371 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: business and finance: 1348 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: writing and language: 1364 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: entertainment and media: 1347 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- Kagi LLM Benchmark: 69.4% (source: Kagi LLM Benchmarking Project, read October 22, 2026)
- SciCode: 4.6% (source: Kaggle Benchmarks, read October 22, 2026)